Decentralized Multitask Learning over Learned Task Graphs

The paper presents a decentralized multitask learning framework that learns task relationships directly from distributed data. It introduces a two‑phase strategy: first estimating a generalized graph Laplacian from noisy stochastic gradient iterates, then using the learned graph to facilitate cooperative multitask diffusion learning. The authors provide theoretical analysis of Laplacian estimation error, its impact on steady‑state performance, and a topology sensitivity index, and confirm the benefits of learned task graphs through simulations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• diffusion